| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9985815602836879, | |
| "eval_steps": 500, | |
| "global_step": 176, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005673758865248227, | |
| "grad_norm": 23.321381386134785, | |
| "learning_rate": 5.555555555555555e-07, | |
| "loss": 1.3529, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028368794326241134, | |
| "grad_norm": 8.891056445208546, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 1.2787, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": 4.590231197414839, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 1.0257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 3.142582341930927, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.8807, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 2.843802286813948, | |
| "learning_rate": 9.99604698613651e-06, | |
| "loss": 0.843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14184397163120568, | |
| "grad_norm": 2.4374270657643065, | |
| "learning_rate": 9.951647332362511e-06, | |
| "loss": 0.8103, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 2.3244501516240073, | |
| "learning_rate": 9.85834670020205e-06, | |
| "loss": 0.778, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19858156028368795, | |
| "grad_norm": 2.3307590830855576, | |
| "learning_rate": 9.717066498610673e-06, | |
| "loss": 0.7493, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 2.867283965545168, | |
| "learning_rate": 9.529201968327618e-06, | |
| "loss": 0.7304, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 2.503845781291395, | |
| "learning_rate": 9.296608402898306e-06, | |
| "loss": 0.711, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 2.4532179305680364, | |
| "learning_rate": 9.021582826353825e-06, | |
| "loss": 0.6915, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3120567375886525, | |
| "grad_norm": 2.133742309031153, | |
| "learning_rate": 8.706841308493092e-06, | |
| "loss": 0.6713, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 2.3597738337675187, | |
| "learning_rate": 8.355492141795185e-06, | |
| "loss": 0.6476, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.36879432624113473, | |
| "grad_norm": 2.41256063962414, | |
| "learning_rate": 7.971005144858554e-06, | |
| "loss": 0.6409, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3971631205673759, | |
| "grad_norm": 2.5863453080504275, | |
| "learning_rate": 7.5571773955171124e-06, | |
| "loss": 0.6307, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 2.1230662364450525, | |
| "learning_rate": 7.118095732042643e-06, | |
| "loss": 0.6241, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 2.339842319600617, | |
| "learning_rate": 6.65809639276034e-06, | |
| "loss": 0.61, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.48226950354609927, | |
| "grad_norm": 2.203220986165918, | |
| "learning_rate": 6.181722192664526e-06, | |
| "loss": 0.607, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 2.057055175195757, | |
| "learning_rate": 5.693677659945343e-06, | |
| "loss": 0.568, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5390070921985816, | |
| "grad_norm": 2.0107641524633713, | |
| "learning_rate": 5.19878257548463e-06, | |
| "loss": 0.5581, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 2.342751630632786, | |
| "learning_rate": 4.701924374150901e-06, | |
| "loss": 0.5588, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 2.039824613266622, | |
| "learning_rate": 4.2080098779639255e-06, | |
| "loss": 0.5543, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.624113475177305, | |
| "grad_norm": 2.1842313088053107, | |
| "learning_rate": 3.721916837797627e-06, | |
| "loss": 0.5382, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6524822695035462, | |
| "grad_norm": 2.3866340812713456, | |
| "learning_rate": 3.2484457621808787e-06, | |
| "loss": 0.5336, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 2.3598347444604637, | |
| "learning_rate": 2.792272508920443e-06, | |
| "loss": 0.5298, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "grad_norm": 2.194353937213305, | |
| "learning_rate": 2.3579021077369047e-06, | |
| "loss": 0.5092, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7375886524822695, | |
| "grad_norm": 2.2206104013150805, | |
| "learning_rate": 1.949624269947378e-06, | |
| "loss": 0.5163, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 2.2710578602998623, | |
| "learning_rate": 1.5714710245679348e-06, | |
| "loss": 0.5106, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": 2.0376221819656752, | |
| "learning_rate": 1.227176899208849e-06, | |
| "loss": 0.5101, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8226950354609929, | |
| "grad_norm": 2.0283659113726586, | |
| "learning_rate": 9.201420390041965e-07, | |
| "loss": 0.5071, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 2.008652811277033, | |
| "learning_rate": 6.533986278020876e-07, | |
| "loss": 0.4827, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8794326241134752, | |
| "grad_norm": 2.0949057219648286, | |
| "learning_rate": 4.2958094322982703e-07, | |
| "loss": 0.5023, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": 2.139405991925096, | |
| "learning_rate": 2.5089934136108665e-07, | |
| "loss": 0.4934, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 2.0539208771983923, | |
| "learning_rate": 1.1911842790474637e-07, | |
| "loss": 0.489, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9645390070921985, | |
| "grad_norm": 1.9792159065875536, | |
| "learning_rate": 3.553963149013295e-08, | |
| "loss": 0.4794, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9929078014184397, | |
| "grad_norm": 1.9554520695912883, | |
| "learning_rate": 9.883511496722176e-10, | |
| "loss": 0.4721, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9985815602836879, | |
| "eval_loss": 0.6546463370323181, | |
| "eval_runtime": 96.7348, | |
| "eval_samples_per_second": 3.122, | |
| "eval_steps_per_second": 0.786, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.9985815602836879, | |
| "step": 176, | |
| "total_flos": 36798474485760.0, | |
| "train_loss": 0.6350141577422619, | |
| "train_runtime": 4225.9013, | |
| "train_samples_per_second": 1.333, | |
| "train_steps_per_second": 0.042 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 176, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 36798474485760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |